You have opted out of job matches in .
To undo this, go to the 'Skills and Interests' section of your preferences.
Shared by 
3 days ago
Requirements and responsibilities
Joveo Ai is hiring LLM Engineers to build and ship production-grade AI systems powered by large language models—covering RAG pipelines, evaluation systems, and intelligent features that transform how employers and job seekers connect.About Joveo AiEvery company says they're "AI-first." Joveo actually is. Their recruitment advertising platform processes millions of hiring decisions using machine learning, real-time bidding, and predictive analytics—helping the world's largest employers hire faster and smarter.About the RoleYou will architect and deliver LLM-powered systems in production. This includes building RAG pipelines, designing evaluation frameworks, and integrating AI deeply into real-world hiring workflows.What You Will DoDesign and build LLM-powered applications (RAG systems + agentic workflows)Fine-tune, evaluate, and optimize LLMs for recruitment use casesBuild prompt engineering frameworks and manage prompt versioning at scaleDevelop evaluation + benchmarking pipelines for quality and safetyIntegrate LLMs with APIs, databases, and internal systemsMonitor production performance (latency, cost, hallucinations, quality)Required QualificationsStrong hands-on experience building LLM applications in productionSolid Python + software engineering fundamentalsExperience with LangChain, LlamaIndex, DSPy, or similar frameworksKnowledge of RAG architectures and vector databases (Pinecone, Weaviate, pgvector)Familiarity with OpenAI, Anthropic, Google, or open-source model APIsExperience with LLM evaluation (RAGAS, benchmarks, human feedback)Equal OpportunityJoveo is committed to building an inclusive workplace. All hiring decisions are based on skills, qualifications, and ability—welcoming candidates from all backgrounds.
Optionally, you can add more information later (benefits, pre-screening questions, etc.)